Matches in SemOpenAlex for { <https://semopenalex.org/work/W3158045251> ?p ?o ?g. }
Showing items 1 to 70 of
70
with 100 items per page.
- W3158045251 abstract "Abstract As deep learning is increasingly applied to segmentation of organs from Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) sequences, we should understand the importance of certain operations that can improve the quality of results. For segmentation of the liver from those sequences, we quantify the improvement achieved with segmentation network, loss function and post-processing steps. Our results on a publicly available dataset show an improvement of 11% points (pp) by using DeepLabV3 instead of UNet or FCN, 4 pp by applying post-processing operations and 2pp using the top-performing loss function. The conclusions of this work help researchers and practitioners choosing the network and loss function and implementing effective post-processing operations." @default.
- W3158045251 created "2021-05-10" @default.
- W3158045251 creator A5049382757 @default.
- W3158045251 date "2021-01-01" @default.
- W3158045251 modified "2023-09-24" @default.
- W3158045251 title "Loss, post-processing and standard architecture improvements of liver deep learning segmentation from Computed Tomography and magnetic resonance" @default.
- W3158045251 cites W1504916455 @default.
- W3158045251 cites W2010099973 @default.
- W3158045251 cites W2115297331 @default.
- W3158045251 cites W2124204401 @default.
- W3158045251 cites W2412782625 @default.
- W3158045251 cites W2551560790 @default.
- W3158045251 cites W2555096873 @default.
- W3158045251 cites W2606378806 @default.
- W3158045251 cites W2799142782 @default.
- W3158045251 cites W288721753 @default.
- W3158045251 cites W2894315883 @default.
- W3158045251 cites W2945683845 @default.
- W3158045251 cites W2947035448 @default.
- W3158045251 doi "https://doi.org/10.1016/j.imu.2021.100585" @default.
- W3158045251 hasPublicationYear "2021" @default.
- W3158045251 type Work @default.
- W3158045251 sameAs 3158045251 @default.
- W3158045251 citedByCount "0" @default.
- W3158045251 crossrefType "journal-article" @default.
- W3158045251 hasAuthorship W3158045251A5049382757 @default.
- W3158045251 hasBestOaLocation W31580452511 @default.
- W3158045251 hasConcept C121332964 @default.
- W3158045251 hasConcept C123657996 @default.
- W3158045251 hasConcept C126838900 @default.
- W3158045251 hasConcept C142362112 @default.
- W3158045251 hasConcept C143409427 @default.
- W3158045251 hasConcept C153349607 @default.
- W3158045251 hasConcept C154945302 @default.
- W3158045251 hasConcept C41008148 @default.
- W3158045251 hasConcept C46141821 @default.
- W3158045251 hasConcept C544519230 @default.
- W3158045251 hasConcept C71924100 @default.
- W3158045251 hasConcept C89600930 @default.
- W3158045251 hasConceptScore W3158045251C121332964 @default.
- W3158045251 hasConceptScore W3158045251C123657996 @default.
- W3158045251 hasConceptScore W3158045251C126838900 @default.
- W3158045251 hasConceptScore W3158045251C142362112 @default.
- W3158045251 hasConceptScore W3158045251C143409427 @default.
- W3158045251 hasConceptScore W3158045251C153349607 @default.
- W3158045251 hasConceptScore W3158045251C154945302 @default.
- W3158045251 hasConceptScore W3158045251C41008148 @default.
- W3158045251 hasConceptScore W3158045251C46141821 @default.
- W3158045251 hasConceptScore W3158045251C544519230 @default.
- W3158045251 hasConceptScore W3158045251C71924100 @default.
- W3158045251 hasConceptScore W3158045251C89600930 @default.
- W3158045251 hasLocation W31580452511 @default.
- W3158045251 hasLocation W31580452512 @default.
- W3158045251 hasLocation W31580452513 @default.
- W3158045251 hasOpenAccess W3158045251 @default.
- W3158045251 hasPrimaryLocation W31580452511 @default.
- W3158045251 hasRelatedWork W1964496343 @default.
- W3158045251 hasRelatedWork W2006341426 @default.
- W3158045251 hasRelatedWork W2025378574 @default.
- W3158045251 hasRelatedWork W2083053675 @default.
- W3158045251 hasRelatedWork W2089910129 @default.
- W3158045251 hasRelatedWork W2399057966 @default.
- W3158045251 hasRelatedWork W2465706935 @default.
- W3158045251 hasRelatedWork W2574578019 @default.
- W3158045251 hasRelatedWork W2889577114 @default.
- W3158045251 hasRelatedWork W1972217857 @default.
- W3158045251 isParatext "false" @default.
- W3158045251 isRetracted "false" @default.
- W3158045251 magId "3158045251" @default.
- W3158045251 workType "article" @default.